def text_to_instance(
self, # type: ignore
question_text_list: List[str],
passage_text: str,
start_span_list: List[List[int]] = None,
end_span_list: List[List[int]] = None,
passage_tokens: List[Token] = None,
yesno_list: List[int] = None,
followup_list: List[int] = None,
additional_metadata: Dict[str, Any] = None,
) -> Instance:
# We need to convert character indices in `passage_text` to token indices in
# `passage_tokens`, as the latter is what we'll actually use for supervision.
answer_token_span_list = []
passage_offsets = [(token.idx, token.idx + len(token.text))
for token in passage_tokens]
for start_list, end_list in zip(start_span_list, end_span_list):
token_spans: List[Tuple[int, int]] = []
for char_span_start, char_span_end in zip(start_list, end_list):
(span_start, span_end), error = util.char_span_to_token_span(
passage_offsets, (char_span_start, char_span_end))
if error:
logger.debug("Passage: %s", passage_text)
logger.debug("Passage tokens: %s", passage_tokens)
logger.debug("Answer span: (%d, %d)", char_span_start,
char_span_end)
logger.debug("Token span: (%d, %d)", span_start, span_end)
logger.debug("Tokens in answer: %s",
passage_tokens[span_start:span_end + 1])
logger.debug("Answer: %s",
passage_text[char_span_start:char_span_end])
token_spans.append((span_start, span_end))
answer_token_span_list.append(token_spans)
question_list_tokens = [
self._tokenizer.tokenize(q) for q in question_text_list
]
# Map answer texts to "CANNOTANSWER" if more than half of them marked as so.
additional_metadata["answer_texts_list"] = [
util.handle_cannot(ans_list)
for ans_list in additional_metadata["answer_texts_list"]
]
return util.make_reading_comprehension_instance_quac(
question_list_tokens,
passage_tokens,
self._token_indexers,
passage_text,
answer_token_span_list,
yesno_list,
followup_list,
additional_metadata,
self._num_context_answers,
)
def text_to_instance(self, # type: ignore
question_text_list: List[str],
passage_text: str,
start_span_list: List[List[int]] = None,
end_span_list: List[List[int]] = None,
passage_tokens: List[Token] = None,
yesno_list: List[int] = None,
followup_list: List[int] = None,
additional_metadata: Dict[str, Any] = None) -> Instance:
# pylint: disable=arguments-differ
# We need to convert character indices in `passage_text` to token indices in
# `passage_tokens`, as the latter is what we'll actually use for supervision.
answer_token_span_list = []
passage_offsets = [(token.idx, token.idx + len(token.text)) for token in passage_tokens]
for start_list, end_list in zip(start_span_list, end_span_list):
token_spans: List[Tuple[int, int]] = []
for char_span_start, char_span_end in zip(start_list, end_list):
(span_start, span_end), error = util.char_span_to_token_span(passage_offsets,
(char_span_start, char_span_end))
if error:
logger.debug("Passage: %s", passage_text)
logger.debug("Passage tokens: %s", passage_tokens)
logger.debug("Answer span: (%d, %d)", char_span_start, char_span_end)
logger.debug("Token span: (%d, %d)", span_start, span_end)
logger.debug("Tokens in answer: %s", passage_tokens[span_start:span_end + 1])
logger.debug("Answer: %s", passage_text[char_span_start:char_span_end])
token_spans.append((span_start, span_end))
answer_token_span_list.append(token_spans)
question_list_tokens = [self._tokenizer.tokenize(q) for q in question_text_list]
# Map answer texts to "CANNOTANSWER" if more than half of them marked as so.
additional_metadata['answer_texts_list'] = [util.handle_cannot(ans_list) for ans_list \
in additional_metadata['answer_texts_list']]
return util.make_reading_comprehension_instance_quac(question_list_tokens,
passage_tokens,
self._token_indexers,
passage_text,
answer_token_span_list,
yesno_list,
followup_list,
additional_metadata,
self._num_context_answers)